Deep learning and the Schrödinger equation

  title={Deep learning and the Schr{\"o}dinger equation},
  author={Kyle Mills and Michael A. Spanner and Isaac Tamblyn},
A deep (convolutional) neural network is trained to predict the ground-state energy of an electron in two-dimensional potentials. The machinery of deep learning is developed to learn the mapping between potential and energy, which bypasses the need to numerically solve the Schr\"odinger equation and the need for computing wave functions. 

Figures from this paper

Deep learning methods for the computation of vibrational wavefunctions
  • L. Domingo, F. Borondo
  • Computer Science
    Communications in Nonlinear Science and Numerical Simulation
  • 2021
Neural network approaches for solving Schrödinger equation in arbitrary quantum wells
In this work, two neural networks with different architectures are proposed and trained using a set of potentials, energies, and wave functions previously generated with the classical finite element method to approach the Schrödinger equation in quantum wells with arbitrary potentials using the machine learning technique.
Machine learning and excited-state molecular dynamics
Recent advances for excited-state dynamics based on machine learning in quantum chemistry are surveyed to highlight successes, pitfalls, challenges and future avenues for machine learning approaches for light-induced molecular processes.
Deep neural networks for direct, featureless learning through observation: The case of two-dimensional spin models.
The capability of a convolutional deep neural network in predicting the nearest-neighbor energy of the 4×4 Ising model and the ability of the neural network to recover the phase transition with equivalent accuracy to the numerically exact method are demonstrated.
Extensive deep neural networks for transferring small scale learning to large scale systems
A physically-motivated topology of a deep neural network is presented that can efficiently infer extensive parameters of arbitrarily large systems, doing so with scaling.
Machine learning density functional theory for the Hubbard model
The solution of complex many-body lattice models can often be found by defining an energy functional of the relevant density of the problem. For instance, in the case of the Hubbard model the
Solving frustrated quantum many-particle models with convolutional neural networks
This work designs a brand new convolutional neural network (CNN) to solve challenging frustrated quantum many-particle problems using machine learning and demonstrates, for the first time, of solving the highly frustrated spin-1/2 J$_1$-J$_2$ antiferromagnetic Heisenberg model on square lattices via CNN.
Machine learning for the solution of the Schrödinger equation
  • S. Manzhos
  • Computer Science
    Mach. Learn. Sci. Technol.
  • 2020
This work surveys recent uses of ML techniques to solve the Schrödinger equation, including the vibrational Schr Ödinger equations, the electronic SchröDinger equation and the related problems of constructing functionals for density functional theory (DFT) as well as potentials which enter semi-empirical approximations to DFT.
Deep learning for retrieval of the internuclear distance in a molecule from interference patterns in photoelectron momentum distributions
Abstract We use a convolutional neural network to retrieve the internuclear distance in the twodimensional H+2 molecule ionized by a strong few-cycle laser pulse based on the photoelectron momentum
Learning Potentials of Quantum Systems using Deep Neural Networks
The method, termed Quantum Potential Neural Networks (QPNN), can learn potentials in an unsupervised manner with remarkable accuracy for a wide range of quantum systems, such as the quantum harmonic oscillator, particle in a box perturbed by an external potential, hydrogen atom, Poschl--Teller potential, and a solitary wave system.


Modeling electronic quantum transport with machine learning
The remarkable performance of the machine learning approach to solve electronic quantum transport equations of one-dimensional nanostructures to capture the complexity of interference phenomena lends further support to its viability in dealing with transport problems of undulatory nature.
Machine learning for many-body physics: The case of the Anderson impurity model
Machine learning methods are applied to finding the Green's function of the Anderson impurity model, a basic model system of quantum many-body condensed-matter physics. Different methods of
Kinetic Energy of Hydrocarbons as a Function of Electron Density and Convolutional Neural Networks.
A convolutional neural network trained to reproduce the Kohn-Sham kinetic energy of hydrocarbons from an input electron density is demonstrated and it is shown that this approximation qualitatively reproduces KOHN-Sham potential energy surfaces when used with conventional exchange correlation functionals.
Finding Density Functionals with Machine Learning
For the model problem of the kinetic energy of noninteracting fermions in 1D, mean absolute errors below 1 kcal/mol on test densities similar to the training set are reached with fewer than 100 training densities.
Solving the quantum many-body problem with artificial neural networks
A variational representation of quantum states based on artificial neural networks with a variable number of hidden neurons and a reinforcement-learning scheme that is capable of both finding the ground state and describing the unitary time evolution of complex interacting quantum systems.
Fast and accurate modeling of molecular atomization energies with machine learning.
A machine learning model is introduced to predict atomization energies of a diverse set of organic molecules, based on nuclear charges and atomic positions only, and applicability is demonstrated for the prediction of molecular atomization potential energy curves.
Quantum-chemical insights from deep tensor neural networks
An efficient deep learning approach is developed that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems, and unifies concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks, which leads to size-extensive and uniformly accurate chemical space predictions.
Using neural networks to solve nonlinear differential equations in atomic and molecular physics
To represent the solution of a differential equation by an artificial neural network (ANN) was an idea introduced by Lagaris. Sugawara applied this concept to solve Schrodinger's equation for select